SPDF: A Schedulable Parametric Data-Flow MoC (Extended Version) - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Rapport (Rapport De Recherche) Année : 2011

SPDF: A Schedulable Parametric Data-Flow MoC (Extended Version)

Résumé

Dataflow programming models are suitable to express multi-core streaming applications. The design of high-quality embedded systems in that context requires static analysis to ensure the liveness and bounded memory of the application. However, many streaming applications have a dynamic behavior. The previously proposed dataflow models for dynamic applications do not provide any static guarantees or only in exchange of significant restrictions in expressive power or automation. To overcome these restrictions, we propose the schedulable parametric dataflow (SPDF) model of computation. We present static analyses and a quasi-static scheduling algorithm. We demonstrate our approach using a video decoder case study.
Fichier principal
Vignette du fichier
RR-7828.pdf (886.61 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00666284 , version 1 (03-02-2012)

Identifiants

  • HAL Id : hal-00666284 , version 1

Citer

Pascal Fradet, Alain Girault, Peter Poplavko. SPDF: A Schedulable Parametric Data-Flow MoC (Extended Version). [Research Report] RR-7828, INRIA. 2011, pp.24. ⟨hal-00666284⟩
280 Consultations
182 Téléchargements

Partager

Gmail Facebook X LinkedIn More